Description
At ELCA, large-scale code migrations and refactorings—like upgrading frameworks or moving legacy apps to modern stacks—are time-consuming and repetitive, yet hard to fully automate.
In this internship, you'll explore how LLMs can help automate code migration, producing idiomatic, maintainable code while iteratively fixing errors through testing and refinement. You'll build on ELCA's prototypes and experiment with prompt engineering, fine-tuning, and agent-assisted workflows to create a Proof-of-Concept for a real migration project.
Objectives
* Survey existing tools and techniques for LLM-based code migration
* Implement a Proof-of-Concept using ELCA's prototypes, LLMs, and iterative workflows
* Evaluate where LLMs are effective and when hand-crafted solutions are better
What we offer
* Collaborative, international, tech-driven environment
* Real impact: help improve large-scale software migration processes
* Fun technical events: hackathons, brownbags, and our tech blog
* Monthly after-work events across locations
Skills required
* Knowledge of at least one programming language (Java, TypeScript, Python)
* Strong analytical skills
* Bonus: experience or interest in LLMs and AI-assisted development
Additional information
* Internship starting in February 2026
* Applications must include your most recent academic transcripts
* Candidates must be completing a Master's degree and enrolled in a higher-education program with a valid internship agreement (convention de stage)